05-ux-specification
Pass
Audited by Gen Agent Trust Hub on Sep 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted project documentation such as SRS drafts and user stories to generate a UX specification. This constitutes a potential indirect prompt injection surface, as the agent processes external content to fulfill its primary task.
- Ingestion points:
SKILL.md(Step 1) reads functional requirements and architectural context from files inprojects/<ProjectName>/. - Boundary markers: The instructions do not define explicit delimiters or instructions to ignore potential commands within the ingested content.
- Capability inventory: The skill is limited to reading project files and writing the
UX_Specification.mdoutput; it does not possess high-risk capabilities like arbitrary command execution or external network exfiltration. - Sanitization: No sanitization or validation of the input documentation content is specified.
Audit Metadata